To enhance the adaptability and performance of Convolutional Neural Networks (CNN), we present an adaptable mechanism called Alignable Kernel (AliK) unit, which dynamically adjusts the receptive field (RF) dimensions of a model in response to varying stimuli. The branches of AliK unit are integrated through a novel align transformation softmax attention, incorporating prior knowledge through rank ordering constraints. The attention weightings across the branches establish the effective RF scales, leveraged by neurons in the fusion layer. This mechanism is inspired by neuroscientific observations indicating that the RF dimensions of neurons in the visual cortex vary with the stimulus, a feature often overlooked in CNN architectures. By aggregating successive AliK ensembles, we develop a deep network architecture named the Alignable Kernel Network (AliKNet). AliKNet with interdisciplinary design improves the network’s performance and interpretability by taking direct inspiration from the structure and function of human neural systems, especially the visual cortex. Empirical evaluations in the domains of image classification and semantic segmentation have demonstrated that AliKNet excels over numerous state-of-the-art architectures, achieving this without increasing model complexity. Furthermore, we demonstrate that AliKNet can identify target objects across various scales, confirming their ability to dynamically adapt their RF sizes in response to the input data.

中文翻译：

---

 可对齐的内核网络


为了提高卷积神经网络 （CNN） 的适应性和性能，我们提出了一种称为可对齐核 （AliK） 单元的适应性机制，该机制可以动态调整模型的感受野 （RF） 维度以响应不同的刺激。AliK 单元的分支通过新颖的对齐变换 softmax attention 进行集成，通过排名排序约束整合先验知识。跨分支的注意力权重建立了有效的 RF 量表，由融合层中的神经元利用。这种机制受到神经科学观察的启发，该观察表明视觉皮层中神经元的 RF 尺寸随刺激而变化，这是 CNN 架构中经常被忽视的特征。通过聚合连续的 AliK 集成，我们开发了一个名为 AliKNet 的深度网络架构。采用跨学科设计的 AliKNet 通过从人类神经系统（尤其是视觉皮层）的结构和功能中直接汲取灵感，提高了网络的性能和可解释性。图像分类和语义分割领域的实证评估表明，AliKNet 在众多最先进的架构中表现出色，在不增加模型复杂性的情况下实现了这一目标。此外，我们证明 AliKNet 可以识别各种尺度上的目标物体，证实它们能够根据输入数据动态调整其 RF 大小。